You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello! First of all thanks for your work on the development of this project. I have been trying to use your code to generate explanations for an LSTM model.
I have been following the notebook you provide and adapting it to my use case.
To generate global feature explanations, you make use of the function
Features to be used by the model. Requires same order as training dataset
and it generates the following error:
line 327, in feat_explain_all
sequence = sequence[:, :, model_features]
IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices
Hello! First of all thanks for your work on the development of this project. I have been trying to use your code to generate explanations for an LSTM model.
I have been following the notebook you provide and adapting it to my use case.
To generate global feature explanations, you make use of the function
timeshap/src/timeshap/explainer/feature_level.py
Lines 204 to 215 in b07dd7c
I have been calling with with the arguments suited to my use case, specifically providing it the
model_features
argument (a list of strings)
timeshap/src/timeshap/explainer/feature_level.py
Lines 245 to 246 in b07dd7c
and it generates the following error:
This is the line of code:
timeshap/src/timeshap/explainer/feature_level.py
Lines 326 to 327 in b07dd7c
I have noticed that you create indices above and never use the variable
model_features_index
timeshap/src/timeshap/explainer/feature_level.py
Line 317 in b07dd7c
It makes sense that the array should be accessed with these indexes, rather than with a list of strings, is that it?
The text was updated successfully, but these errors were encountered: